Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    -induced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Filho
    -0.09
    (best
    -0.09
    (system
    -0.08
    ệm
    -0.08
     Об
    -0.08
     投稿日
    -0.07
    افحة
    -0.07
     permitted
    -0.07
    проч
    -0.07
     cấu
    -0.07
    POSITIVE LOGITS
    Creative
    0.08
     kreative
    0.08
     Zebra
    0.08
     Creative
    0.08
     artificially
    0.07
     creative
    0.07
    _fake
    0.07
     mystical
    0.07
    Side
    0.07
    keydown
    0.07
    Act Density 0.001%

    No Known Activations